Hugging Face's logo

yahyaabd
/
allstats-semantic-base-v1

Sentence Similarity
sentence-transformers
Safetensors
xlm-roberta
feature-extraction
Generated from Trainer
dataset_size:123640
loss:CosineSimilarityLoss
Eval Results
text-embeddings-inference
Inference Endpoints
Model card Files Community
yahyaabd commited on
Commit
29e591b
·
verified ·
1 Parent(s): b8772aa

Add new SentenceTransformer model

Browse files
Files changed (11) hide show
  1. .gitattributes +1 -0
  2. 1_Pooling/config.json +10 -0
  3. README.md +499 -0
  4. config.json +29 -0
  5. config_sentence_transformers.json +10 -0
  6. model.safetensors +3 -0
  7. modules.json +14 -0
  8. sentence_bert_config.json +4 -0
  9. special_tokens_map.json +51 -0
  10. tokenizer.json +3 -0
  11. tokenizer_config.json +62 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
1_Pooling/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 768,
3
+ "pooling_mode_cls_token": false,
4
+ "pooling_mode_mean_tokens": true,
5
+ "pooling_mode_max_tokens": false,
6
+ "pooling_mode_mean_sqrt_len_tokens": false,
7
+ "pooling_mode_weightedmean_tokens": false,
8
+ "pooling_mode_lasttoken": false,
9
+ "include_prompt": true
10
+ }
README.md ADDED
@@ -0,0 +1,499 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - sentence-transformers
4
+ - sentence-similarity
5
+ - feature-extraction
6
+ - generated_from_trainer
7
+ - dataset_size:123640
8
+ - loss:CosineSimilarityLoss
9
+ base_model: sentence-transformers/paraphrase-multilingual-mpnet-base-v2
10
+ widget:
11
+ - source_sentence: data perempuan dan laki-laki di indonesia 2022
12
+ sentences:
13
+ - Statistik Telekomunikasi Indonesia 2012
14
+ - Perkembangan Indeks Produksi Triwulanan Industri Mikro dan Kecil 2023
15
+ - Pada Agustus 2014, Jumlah wisman mencapai 826,8 ribu
16
+ - source_sentence: hasil survei kebutuhan data 2011 di indonesia
17
+ sentences:
18
+ - Analisis Survei Kebutuhan Data 2011
19
+ - Produk Domestik Bruto Indonesia Triwulanan 2007-2011
20
+ - Direktori Perusahaan Air Bersih, Listrik, dan Gas 2022
21
+ - source_sentence: komoditas apa yang produksinya naik 3,24 persen pada tahun 2013?
22
+ sentences:
23
+ - Indikator Ekonomi Juni 2017
24
+ - Produksi jagung naik pada tahun 2013.
25
+ - Statistik Keuangan Pemerintah Desa 2018
26
+ - source_sentence: buku-buku statistik tahun 2007
27
+ sentences:
28
+ - Statistik Keuangan Badan Usaha Milik Negara dan Badan Usaha Milik Daerah 2019
29
+ - Statistik Harga Konsumen Perdesaan Kelompok Makanan 2011
30
+ - Buletin Statistik Perdagangan Luar Negeri Impor Mei 2019
31
+ - source_sentence: analisis kinerja ekspor indonesia feb 2014
32
+ sentences:
33
+ - Kajian Big Data Sinyal Pemulihan Indonesia dari Pandemi Covid-19
34
+ - Laporan Bulanan Data Sosial Ekonomi Januari 2019
35
+ - Buletin Statistik Perdagangan Luar Negeri Ekspor Menurut Kelompok Komoditi dan
36
+ Negara Februari 2014
37
+ datasets:
38
+ - yahyaabd/allstats-semantic-synthetic-dataset-v1
39
+ pipeline_tag: sentence-similarity
40
+ library_name: sentence-transformers
41
+ metrics:
42
+ - pearson_cosine
43
+ - spearman_cosine
44
+ model-index:
45
+ - name: SentenceTransformer based on sentence-transformers/paraphrase-multilingual-mpnet-base-v2
46
+ results:
47
+ - task:
48
+ type: semantic-similarity
49
+ name: Semantic Similarity
50
+ dataset:
51
+ name: allstats semantic base v1 eval
52
+ type: allstats-semantic-base-v1-eval
53
+ metrics:
54
+ - type: pearson_cosine
55
+ value: 0.9866451272402678
56
+ name: Pearson Cosine
57
+ - type: spearman_cosine
58
+ value: 0.9032950863870964
59
+ name: Spearman Cosine
60
+ - task:
61
+ type: semantic-similarity
62
+ name: Semantic Similarity
63
+ dataset:
64
+ name: allstat semantic base v1 test
65
+ type: allstat-semantic-base-v1-test
66
+ metrics:
67
+ - type: pearson_cosine
68
+ value: 0.9876833290128094
69
+ name: Pearson Cosine
70
+ - type: spearman_cosine
71
+ value: 0.9063327700749637
72
+ name: Spearman Cosine
73
+ ---
74
+
75
+ # SentenceTransformer based on sentence-transformers/paraphrase-multilingual-mpnet-base-v2
76
+
77
+ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/paraphrase-multilingual-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-mpnet-base-v2) on the [allstats-semantic-synthetic-dataset-v1](https://huggingface.co/datasets/yahyaabd/allstats-semantic-synthetic-dataset-v1) dataset. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
78
+
79
+ ## Model Details
80
+
81
+ ### Model Description
82
+ - **Model Type:** Sentence Transformer
83
+ - **Base model:** [sentence-transformers/paraphrase-multilingual-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-mpnet-base-v2) <!-- at revision 75c57757a97f90ad739aca51fa8bfea0e485a7f2 -->
84
+ - **Maximum Sequence Length:** 128 tokens
85
+ - **Output Dimensionality:** 768 dimensions
86
+ - **Similarity Function:** Cosine Similarity
87
+ - **Training Dataset:**
88
+ - [allstats-semantic-synthetic-dataset-v1](https://huggingface.co/datasets/yahyaabd/allstats-semantic-synthetic-dataset-v1)
89
+ <!-- - **Language:** Unknown -->
90
+ <!-- - **License:** Unknown -->
91
+
92
+ ### Model Sources
93
+
94
+ - **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
95
+ - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
96
+ - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
97
+
98
+ ### Full Model Architecture
99
+
100
+ ```
101
+ SentenceTransformer(
102
+ (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: XLMRobertaModel
103
+ (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
104
+ )
105
+ ```
106
+
107
+ ## Usage
108
+
109
+ ### Direct Usage (Sentence Transformers)
110
+
111
+ First install the Sentence Transformers library:
112
+
113
+ ```bash
114
+ pip install -U sentence-transformers
115
+ ```
116
+
117
+ Then you can load this model and run inference.
118
+ ```python
119
+ from sentence_transformers import SentenceTransformer
120
+
121
+ # Download from the 🤗 Hub
122
+ model = SentenceTransformer("yahyaabd/allstats-semantic-base-v1")
123
+ # Run inference
124
+ sentences = [
125
+ 'analisis kinerja ekspor indonesia feb 2014',
126
+ 'Buletin Statistik Perdagangan Luar Negeri Ekspor Menurut Kelompok Komoditi dan Negara Februari 2014',
127
+ 'Laporan Bulanan Data Sosial Ekonomi Januari 2019',
128
+ ]
129
+ embeddings = model.encode(sentences)
130
+ print(embeddings.shape)
131
+ # [3, 768]
132
+
133
+ # Get the similarity scores for the embeddings
134
+ similarities = model.similarity(embeddings, embeddings)
135
+ print(similarities.shape)
136
+ # [3, 3]
137
+ ```
138
+
139
+ <!--
140
+ ### Direct Usage (Transformers)
141
+
142
+ <details><summary>Click to see the direct usage in Transformers</summary>
143
+
144
+ </details>
145
+ -->
146
+
147
+ <!--
148
+ ### Downstream Usage (Sentence Transformers)
149
+
150
+ You can finetune this model on your own dataset.
151
+
152
+ <details><summary>Click to expand</summary>
153
+
154
+ </details>
155
+ -->
156
+
157
+ <!--
158
+ ### Out-of-Scope Use
159
+
160
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
161
+ -->
162
+
163
+ ## Evaluation
164
+
165
+ ### Metrics
166
+
167
+ #### Semantic Similarity
168
+
169
+ * Datasets: `allstats-semantic-base-v1-eval` and `allstat-semantic-base-v1-test`
170
+ * Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
171
+
172
+ | Metric | allstats-semantic-base-v1-eval | allstat-semantic-base-v1-test |
173
+ |:--------------------|:-------------------------------|:------------------------------|
174
+ | pearson_cosine | 0.9866 | 0.9877 |
175
+ | **spearman_cosine** | **0.9033** | **0.9063** |
176
+
177
+ <!--
178
+ ## Bias, Risks and Limitations
179
+
180
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
181
+ -->
182
+
183
+ <!--
184
+ ### Recommendations
185
+
186
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
187
+ -->
188
+
189
+ ## Training Details
190
+
191
+ ### Training Dataset
192
+
193
+ #### allstats-semantic-synthetic-dataset-v1
194
+
195
+ * Dataset: [allstats-semantic-synthetic-dataset-v1](https://huggingface.co/datasets/yahyaabd/allstats-semantic-synthetic-dataset-v1) at [d59a245](https://huggingface.co/datasets/yahyaabd/allstats-semantic-synthetic-dataset-v1/tree/d59a24585b2ee30e806569dc6a091becd5fcac0c)
196
+ * Size: 123,640 training samples
197
+ * Columns: <code>query</code>, <code>doc</code>, and <code>label</code>
198
+ * Approximate statistics based on the first 1000 samples:
199
+ | | query | doc | label |
200
+ |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------|
201
+ | type | string | string | float |
202
+ | details | <ul><li>min: 6 tokens</li><li>mean: 10.64 tokens</li><li>max: 34 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 14.06 tokens</li><li>max: 76 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.49</li><li>max: 1.0</li></ul> |
203
+ * Samples:
204
+ | query | doc | label |
205
+ |:----------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------|:------------------|
206
+ | <code>Gambaran umum karakteristik usaha di Indonesia</code> | <code>Statistik Karakteristik Usaha 2022/2023</code> | <code>0.9</code> |
207
+ | <code>Tabel data jumlah sekolah, guru, dan murid MA di bawah Kementerian Agama per provinsi.</code> | <code>Jumlah Sekolah, Guru, dan Murid Madrasah Aliyah (MA) di Bawah Kementerian Agama Menurut Provinsi, tahun ajaran 2005/2006-2015/2016</code> | <code>0.96</code> |
208
+ | <code>bagaimana kinerja sektor konstruksi indonesia di triwulan ketiga tahun 2008?</code> | <code>Statistik Restoran/Rumah Makan 2007</code> | <code>0.09</code> |
209
+ * Loss: [<code>CosineSimilarityLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters:
210
+ ```json
211
+ {
212
+ "loss_fct": "torch.nn.modules.loss.MSELoss"
213
+ }
214
+ ```
215
+
216
+ ### Evaluation Dataset
217
+
218
+ #### allstats-semantic-synthetic-dataset-v1
219
+
220
+ * Dataset: [allstats-semantic-synthetic-dataset-v1](https://huggingface.co/datasets/yahyaabd/allstats-semantic-synthetic-dataset-v1) at [d59a245](https://huggingface.co/datasets/yahyaabd/allstats-semantic-synthetic-dataset-v1/tree/d59a24585b2ee30e806569dc6a091becd5fcac0c)
221
+ * Size: 26,494 evaluation samples
222
+ * Columns: <code>query</code>, <code>doc</code>, and <code>label</code>
223
+ * Approximate statistics based on the first 1000 samples:
224
+ | | query | doc | label |
225
+ |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------|
226
+ | type | string | string | float |
227
+ | details | <ul><li>min: 5 tokens</li><li>mean: 10.48 tokens</li><li>max: 34 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 13.86 tokens</li><li>max: 58 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.49</li><li>max: 1.0</li></ul> |
228
+ * Samples:
229
+ | query | doc | label |
230
+ |:-----------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------|:------------------|
231
+ | <code>Harga barang konsumsi Indonesia 2022: data per kota</code> | <code>Harga Konsumen Beberapa Barang Kelompok Makanan, Minuman, dan Tembakau 90 Kota di Indonesia 2022</code> | <code>0.92</code> |
232
+ | <code>data biaya hidup bali 2018</code> | <code>Buletin Statistik Perdagangan Luar Negeri Ekspor Menurut Kelompok Komoditi dan Negara, Maret 2018</code> | <code>0.1</code> |
233
+ | <code>ekspor barang indonesia november 2011: data lengkap</code> | <code>Buletin Statistik Perdagangan Luar Negeri Ekspor Menurut Kelompok Komoditi dan Negara Februari 2013</code> | <code>0.12</code> |
234
+ * Loss: [<code>CosineSimilarityLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters:
235
+ ```json
236
+ {
237
+ "loss_fct": "torch.nn.modules.loss.MSELoss"
238
+ }
239
+ ```
240
+
241
+ ### Training Hyperparameters
242
+ #### Non-Default Hyperparameters
243
+
244
+ - `eval_strategy`: steps
245
+ - `per_device_train_batch_size`: 32
246
+ - `per_device_eval_batch_size`: 32
247
+ - `num_train_epochs`: 10
248
+ - `warmup_ratio`: 0.1
249
+ - `fp16`: True
250
+ - `load_best_model_at_end`: True
251
+
252
+ #### All Hyperparameters
253
+ <details><summary>Click to expand</summary>
254
+
255
+ - `overwrite_output_dir`: False
256
+ - `do_predict`: False
257
+ - `eval_strategy`: steps
258
+ - `prediction_loss_only`: True
259
+ - `per_device_train_batch_size`: 32
260
+ - `per_device_eval_batch_size`: 32
261
+ - `per_gpu_train_batch_size`: None
262
+ - `per_gpu_eval_batch_size`: None
263
+ - `gradient_accumulation_steps`: 1
264
+ - `eval_accumulation_steps`: None
265
+ - `torch_empty_cache_steps`: None
266
+ - `learning_rate`: 5e-05
267
+ - `weight_decay`: 0.0
268
+ - `adam_beta1`: 0.9
269
+ - `adam_beta2`: 0.999
270
+ - `adam_epsilon`: 1e-08
271
+ - `max_grad_norm`: 1.0
272
+ - `num_train_epochs`: 10
273
+ - `max_steps`: -1
274
+ - `lr_scheduler_type`: linear
275
+ - `lr_scheduler_kwargs`: {}
276
+ - `warmup_ratio`: 0.1
277
+ - `warmup_steps`: 0
278
+ - `log_level`: passive
279
+ - `log_level_replica`: warning
280
+ - `log_on_each_node`: True
281
+ - `logging_nan_inf_filter`: True
282
+ - `save_safetensors`: True
283
+ - `save_on_each_node`: False
284
+ - `save_only_model`: False
285
+ - `restore_callback_states_from_checkpoint`: False
286
+ - `no_cuda`: False
287
+ - `use_cpu`: False
288
+ - `use_mps_device`: False
289
+ - `seed`: 42
290
+ - `data_seed`: None
291
+ - `jit_mode_eval`: False
292
+ - `use_ipex`: False
293
+ - `bf16`: False
294
+ - `fp16`: True
295
+ - `fp16_opt_level`: O1
296
+ - `half_precision_backend`: auto
297
+ - `bf16_full_eval`: False
298
+ - `fp16_full_eval`: False
299
+ - `tf32`: None
300
+ - `local_rank`: 0
301
+ - `ddp_backend`: None
302
+ - `tpu_num_cores`: None
303
+ - `tpu_metrics_debug`: False
304
+ - `debug`: []
305
+ - `dataloader_drop_last`: False
306
+ - `dataloader_num_workers`: 0
307
+ - `dataloader_prefetch_factor`: None
308
+ - `past_index`: -1
309
+ - `disable_tqdm`: False
310
+ - `remove_unused_columns`: True
311
+ - `label_names`: None
312
+ - `load_best_model_at_end`: True
313
+ - `ignore_data_skip`: False
314
+ - `fsdp`: []
315
+ - `fsdp_min_num_params`: 0
316
+ - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
317
+ - `fsdp_transformer_layer_cls_to_wrap`: None
318
+ - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
319
+ - `deepspeed`: None
320
+ - `label_smoothing_factor`: 0.0
321
+ - `optim`: adamw_torch
322
+ - `optim_args`: None
323
+ - `adafactor`: False
324
+ - `group_by_length`: False
325
+ - `length_column_name`: length
326
+ - `ddp_find_unused_parameters`: None
327
+ - `ddp_bucket_cap_mb`: None
328
+ - `ddp_broadcast_buffers`: False
329
+ - `dataloader_pin_memory`: True
330
+ - `dataloader_persistent_workers`: False
331
+ - `skip_memory_metrics`: True
332
+ - `use_legacy_prediction_loop`: False
333
+ - `push_to_hub`: False
334
+ - `resume_from_checkpoint`: None
335
+ - `hub_model_id`: None
336
+ - `hub_strategy`: every_save
337
+ - `hub_private_repo`: None
338
+ - `hub_always_push`: False
339
+ - `gradient_checkpointing`: False
340
+ - `gradient_checkpointing_kwargs`: None
341
+ - `include_inputs_for_metrics`: False
342
+ - `include_for_metrics`: []
343
+ - `eval_do_concat_batches`: True
344
+ - `fp16_backend`: auto
345
+ - `push_to_hub_model_id`: None
346
+ - `push_to_hub_organization`: None
347
+ - `mp_parameters`:
348
+ - `auto_find_batch_size`: False
349
+ - `full_determinism`: False
350
+ - `torchdynamo`: None
351
+ - `ray_scope`: last
352
+ - `ddp_timeout`: 1800
353
+ - `torch_compile`: False
354
+ - `torch_compile_backend`: None
355
+ - `torch_compile_mode`: None
356
+ - `dispatch_batches`: None
357
+ - `split_batches`: None
358
+ - `include_tokens_per_second`: False
359
+ - `include_num_input_tokens_seen`: False
360
+ - `neftune_noise_alpha`: None
361
+ - `optim_target_modules`: None
362
+ - `batch_eval_metrics`: False
363
+ - `eval_on_start`: False
364
+ - `use_liger_kernel`: False
365
+ - `eval_use_gather_object`: False
366
+ - `average_tokens_across_devices`: False
367
+ - `prompts`: None
368
+ - `batch_sampler`: batch_sampler
369
+ - `multi_dataset_batch_sampler`: proportional
370
+
371
+ </details>
372
+
373
+ ### Training Logs
374
+ | Epoch | Step | Training Loss | Validation Loss | allstats-semantic-base-v1-eval_spearman_cosine | allstat-semantic-base-v1-test_spearman_cosine |
375
+ |:----------:|:---------:|:-------------:|:---------------:|:----------------------------------------------:|:---------------------------------------------:|
376
+ | 0.1294 | 500 | 0.0454 | 0.0267 | 0.7374 | - |
377
+ | 0.2588 | 1000 | 0.0243 | 0.0205 | 0.7527 | - |
378
+ | 0.3882 | 1500 | 0.0199 | 0.0169 | 0.7720 | - |
379
+ | 0.5176 | 2000 | 0.0186 | 0.0164 | 0.7733 | - |
380
+ | 0.6470 | 2500 | 0.0179 | 0.0158 | 0.7806 | - |
381
+ | 0.7764 | 3000 | 0.0158 | 0.0155 | 0.7826 | - |
382
+ | 0.9058 | 3500 | 0.0159 | 0.0155 | 0.7771 | - |
383
+ | 1.0352 | 4000 | 0.0155 | 0.0143 | 0.7847 | - |
384
+ | 1.1646 | 4500 | 0.0133 | 0.0141 | 0.7935 | - |
385
+ | 1.2940 | 5000 | 0.0128 | 0.0132 | 0.7986 | - |
386
+ | 1.4234 | 5500 | 0.0121 | 0.0120 | 0.8148 | - |
387
+ | 1.5528 | 6000 | 0.012 | 0.0118 | 0.8030 | - |
388
+ | 1.6822 | 6500 | 0.0118 | 0.0121 | 0.8132 | - |
389
+ | 1.8116 | 7000 | 0.0119 | 0.0109 | 0.8130 | - |
390
+ | 1.9410 | 7500 | 0.0107 | 0.0108 | 0.8132 | - |
391
+ | 2.0704 | 8000 | 0.009 | 0.0098 | 0.8181 | - |
392
+ | 2.1998 | 8500 | 0.0082 | 0.0099 | 0.8221 | - |
393
+ | 2.3292 | 9000 | 0.008 | 0.0100 | 0.8221 | - |
394
+ | 2.4586 | 9500 | 0.008 | 0.0095 | 0.8302 | - |
395
+ | 2.5880 | 10000 | 0.0083 | 0.0090 | 0.8284 | - |
396
+ | 2.7174 | 10500 | 0.0084 | 0.0093 | 0.8261 | - |
397
+ | 2.8468 | 11000 | 0.0084 | 0.0089 | 0.8283 | - |
398
+ | 2.9762 | 11500 | 0.0083 | 0.0093 | 0.8259 | - |
399
+ | 3.1056 | 12000 | 0.0056 | 0.0083 | 0.8362 | - |
400
+ | 3.2350 | 12500 | 0.006 | 0.0081 | 0.8357 | - |
401
+ | 3.3644 | 13000 | 0.0057 | 0.0078 | 0.8381 | - |
402
+ | 3.4938 | 13500 | 0.006 | 0.0081 | 0.8399 | - |
403
+ | 3.6232 | 14000 | 0.0058 | 0.0078 | 0.8420 | - |
404
+ | 3.7526 | 14500 | 0.0068 | 0.0078 | 0.8303 | - |
405
+ | 3.8820 | 15000 | 0.0056 | 0.0072 | 0.8502 | - |
406
+ | 4.0114 | 15500 | 0.0054 | 0.0073 | 0.8483 | - |
407
+ | 4.1408 | 16000 | 0.004 | 0.0068 | 0.8565 | - |
408
+ | 4.2702 | 16500 | 0.0042 | 0.0069 | 0.8493 | - |
409
+ | 4.3996 | 17000 | 0.0043 | 0.0069 | 0.8507 | - |
410
+ | 4.5290 | 17500 | 0.0045 | 0.0069 | 0.8536 | - |
411
+ | 4.6584 | 18000 | 0.0042 | 0.0064 | 0.8602 | - |
412
+ | 4.7878 | 18500 | 0.0043 | 0.0065 | 0.8537 | - |
413
+ | 4.9172 | 19000 | 0.0039 | 0.0062 | 0.8623 | - |
414
+ | 5.0466 | 19500 | 0.0041 | 0.0065 | 0.8601 | - |
415
+ | 5.1760 | 20000 | 0.0032 | 0.0060 | 0.8643 | - |
416
+ | 5.3054 | 20500 | 0.0032 | 0.0064 | 0.8657 | - |
417
+ | 5.4348 | 21000 | 0.0032 | 0.0062 | 0.8669 | - |
418
+ | 5.5642 | 21500 | 0.0031 | 0.0065 | 0.8633 | - |
419
+ | 5.6936 | 22000 | 0.003 | 0.0059 | 0.8682 | - |
420
+ | 5.8230 | 22500 | 0.0032 | 0.0057 | 0.8713 | - |
421
+ | 5.9524 | 23000 | 0.0032 | 0.0057 | 0.8688 | - |
422
+ | 6.0818 | 23500 | 0.0026 | 0.0055 | 0.8772 | - |
423
+ | 6.2112 | 24000 | 0.0023 | 0.0056 | 0.8708 | - |
424
+ | 6.3406 | 24500 | 0.0029 | 0.0056 | 0.8734 | - |
425
+ | 6.4700 | 25000 | 0.0027 | 0.0054 | 0.8748 | - |
426
+ | 6.5994 | 25500 | 0.0022 | 0.0054 | 0.8827 | - |
427
+ | 6.7288 | 26000 | 0.0021 | 0.0053 | 0.8823 | - |
428
+ | 6.8582 | 26500 | 0.0021 | 0.0053 | 0.8832 | - |
429
+ | 6.9876 | 27000 | 0.0025 | 0.0052 | 0.8839 | - |
430
+ | 7.1170 | 27500 | 0.002 | 0.0051 | 0.8887 | - |
431
+ | 7.2464 | 28000 | 0.0017 | 0.0050 | 0.8869 | - |
432
+ | 7.3758 | 28500 | 0.0019 | 0.0052 | 0.8845 | - |
433
+ | 7.5052 | 29000 | 0.0017 | 0.0051 | 0.8897 | - |
434
+ | 7.6346 | 29500 | 0.0017 | 0.0051 | 0.8920 | - |
435
+ | 7.7640 | 30000 | 0.0018 | 0.0050 | 0.8889 | - |
436
+ | 7.8934 | 30500 | 0.0019 | 0.0050 | 0.8931 | - |
437
+ | 8.0228 | 31000 | 0.002 | 0.0049 | 0.8889 | - |
438
+ | 8.1522 | 31500 | 0.0014 | 0.0049 | 0.8912 | - |
439
+ | 8.2816 | 32000 | 0.0013 | 0.0049 | 0.8922 | - |
440
+ | 8.4110 | 32500 | 0.0014 | 0.0049 | 0.8947 | - |
441
+ | 8.5404 | 33000 | 0.0014 | 0.0049 | 0.8960 | - |
442
+ | 8.6698 | 33500 | 0.0014 | 0.0049 | 0.8972 | - |
443
+ | 8.7992 | 34000 | 0.0014 | 0.0048 | 0.8982 | - |
444
+ | 8.9286 | 34500 | 0.0013 | 0.0048 | 0.9003 | - |
445
+ | 9.0580 | 35000 | 0.0014 | 0.0048 | 0.9001 | - |
446
+ | 9.1874 | 35500 | 0.0012 | 0.0048 | 0.8995 | - |
447
+ | 9.3168 | 36000 | 0.0011 | 0.0048 | 0.9008 | - |
448
+ | 9.4462 | 36500 | 0.001 | 0.0047 | 0.9015 | - |
449
+ | 9.5756 | 37000 | 0.0011 | 0.0047 | 0.9026 | - |
450
+ | 9.7050 | 37500 | 0.0011 | 0.0047 | 0.9027 | - |
451
+ | 9.8344 | 38000 | 0.001 | 0.0047 | 0.9035 | - |
452
+ | **9.9638** | **38500** | **0.0011** | **0.0047** | **0.9033** | **-** |
453
+ | 10.0 | 38640 | - | - | - | 0.9063 |
454
+
455
+ * The bold row denotes the saved checkpoint.
456
+
457
+ ### Framework Versions
458
+ - Python: 3.10.12
459
+ - Sentence Transformers: 3.3.1
460
+ - Transformers: 4.47.1
461
+ - PyTorch: 2.5.1+cu124
462
+ - Accelerate: 1.2.1
463
+ - Datasets: 3.2.0
464
+ - Tokenizers: 0.21.0
465
+
466
+ ## Citation
467
+
468
+ ### BibTeX
469
+
470
+ #### Sentence Transformers
471
+ ```bibtex
472
+ @inproceedings{reimers-2019-sentence-bert,
473
+ title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
474
+ author = "Reimers, Nils and Gurevych, Iryna",
475
+ booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
476
+ month = "11",
477
+ year = "2019",
478
+ publisher = "Association for Computational Linguistics",
479
+ url = "https://arxiv.org/abs/1908.10084",
480
+ }
481
+ ```
482
+
483
+ <!--
484
+ ## Glossary
485
+
486
+ *Clearly define terms in order to be accessible across audiences.*
487
+ -->
488
+
489
+ <!--
490
+ ## Model Card Authors
491
+
492
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
493
+ -->
494
+
495
+ <!--
496
+ ## Model Card Contact
497
+
498
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
499
+ -->
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "sentence-transformers/paraphrase-multilingual-mpnet-base-v2",
3
+ "architectures": [
4
+ "XLMRobertaModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "layer_norm_eps": 1e-05,
17
+ "max_position_embeddings": 514,
18
+ "model_type": "xlm-roberta",
19
+ "num_attention_heads": 12,
20
+ "num_hidden_layers": 12,
21
+ "output_past": true,
22
+ "pad_token_id": 1,
23
+ "position_embedding_type": "absolute",
24
+ "torch_dtype": "float32",
25
+ "transformers_version": "4.47.1",
26
+ "type_vocab_size": 1,
27
+ "use_cache": true,
28
+ "vocab_size": 250002
29
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "3.3.1",
4
+ "transformers": "4.47.1",
5
+ "pytorch": "2.5.1+cu124"
6
+ },
7
+ "prompts": {},
8
+ "default_prompt_name": null,
9
+ "similarity_fn_name": "cosine"
10
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61bc45bbbde4092b69714efcf3d8802008ef0b7ec4e22fed0eedbd84c2d53258
3
+ size 1112197096
modules.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "idx": 0,
4
+ "name": "0",
5
+ "path": "",
6
+ "type": "sentence_transformers.models.Transformer"
7
+ },
8
+ {
9
+ "idx": 1,
10
+ "name": "1",
11
+ "path": "1_Pooling",
12
+ "type": "sentence_transformers.models.Pooling"
13
+ }
14
+ ]
sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 128,
3
+ "do_lower_case": false
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cad551d5600a84242d0973327029452a1e3672ba6313c2a3c3d69c4310e12719
3
+ size 17082987
tokenizer_config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "250001": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": false,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "extra_special_tokens": {},
49
+ "mask_token": "<mask>",
50
+ "max_length": 128,
51
+ "model_max_length": 128,
52
+ "pad_to_multiple_of": null,
53
+ "pad_token": "<pad>",
54
+ "pad_token_type_id": 0,
55
+ "padding_side": "right",
56
+ "sep_token": "</s>",
57
+ "stride": 0,
58
+ "tokenizer_class": "XLMRobertaTokenizer",
59
+ "truncation_side": "right",
60
+ "truncation_strategy": "longest_first",
61
+ "unk_token": "<unk>"
62
+ }